XPENG, PKU and HKU Open-Source GroundingPI: Three Visual Grounding Models on the Hub
AdinaYakup · x · 2026-10-14
A collaboration between XPENG, Peking University and HKU, the GroundingPI project open-sources three visual grounding models with demos and papers on Hugging Face:
- GroundingPI: a 4B foundation model covering multiple grounding capabilities such as detection, pointing and OCR.
- GroundAnything: faster grounding via diffusion-based parallel decoding.
- GroundAnything VLM: high-accuracy grounding with an autoregressive VLM.
Related event: XPeng open-sources GroundingPI vision grounding models with PKU and HKU(4 posts)→
More from Research
- AlphaNIST: one RL policy solves all 20 NIST assembly tasks with 98.2% success in simulation — hbouammar · 2026-10-15
- Linear Depth Memory: matrix-valued memory tops PreLN and mHC on DepthBench across scales — SonglinYang4 · 2026-10-15
- Neural field planning for hybrid manufacturing cuts estimated build time 68.3% — jiqizhixin · 2026-10-15
- Tev-Gym: 1,170 dense-reward RL environments push long-horizon agentic training — RulinShao · 2026-10-15
- Claude systematically debunks the speculative EDAR-selenium hypothesis about East Asians — teortaxesTex · 2026-10-15
- Microsoft's AutoEnvScaling lets agents build their own RL environments, lifting Qwen3 Terminal-Bench from 41.1 to 53.3 — omarsar0 · 2026-10-15